Aithus Chenjie Mao

I am a researcher in machine learning, currently affiliated with Shanghai Artificial Intelligence Laboratory as a research assistant. My research interests encompass a broad range of topics in learning theory, including reinforcement learning, online learning, and deep learning theory. Recently, I have focused primarily on the statistical aspects of (offline) reinforcement learning, especially its non-asymptotic behaviors and extensions to reinforcement learning with human feedback (RLHF).

Publication

1. A Fast Convergence Theory for Offline Decision Making
   Chenjie Mao, Qiaosheng Zhang
   Preprint, in submitting

2. On the Role of General Function Approximation in Offline Reinforcement Learning
   Chenjie Mao, Qiaosheng Zhang, Zhen Wang, Xuelong Li
   International Conference on Learning Representations (ICLR), 2024. (Spotlight, Top 5%)

3. Offline Reinforcement Learning with Additional Covering Distributions
   Chenjie Mao
   Transactions on Machine Learning Research (TMLR)